"""
Example usage of NLP Text Analysis Bot
Developer: RSK World
Website: https://rskworld.in
Email: help@rskworld.in
Phone: +91 93305 39277
Year: 2026
"""

from nlp_pipeline import NLPPipeline

def main():
    """
    Example usage of the NLP pipeline
    Developer: RSK World - https://rskworld.in
    """
    # Initialize the NLP pipeline
    print("Initializing NLP Pipeline...")
    pipeline = NLPPipeline()
    
    # Example 1: Product review analysis
    print("\n" + "="*60)
    print("Example 1: Product Review Analysis")
    print("="*60)
    
    review = """
    I absolutely love this new smartphone! The camera quality is amazing 
    and the battery life lasts all day. The design is sleek and modern. 
    However, the price is quite high compared to competitors. Overall, 
    it's a great product from Apple Inc.
    """
    
    results = pipeline.analyze(review)
    print(f"Sentiment: {results['sentiment']['label']}")
    print(f"Score: {results['sentiment']['score']:.3f}")
    print(f"Entities: {len(results['entities']['entities'])} found")
    print(f"Key Topics: {', '.join(results['semantic']['topics'][:3])}")
    
    # Example 2: News article analysis
    print("\n" + "="*60)
    print("Example 2: News Article Analysis")
    print("="*60)
    
    news = """
    Microsoft Corporation announced today that it will be opening a new 
    research facility in Seattle, Washington. The company's CEO, Satya 
    Nadella, stated that this investment will create over 500 jobs and 
    focus on artificial intelligence research. This is great news for 
    the local economy and technology sector.
    """
    
    results = pipeline.analyze(news)
    print(f"Sentiment: {results['sentiment']['label']}")
    print(f"Word Count: {results['summary']['word_count']}")
    print(f"Entities Found: {results['summary']['entity_count']}")
    
    # Print all entities
    print("\nDetected Entities:")
    for entity in results['entities']['entities']:
        print(f"  - {entity['text']} ({entity['label']})")
    
    # Example 3: Social media post
    print("\n" + "="*60)
    print("Example 3: Social Media Post Analysis")
    print("="*60)
    
    post = "Just had the worst experience at the restaurant. Terrible service and cold food. Never going back!"
    
    results = pipeline.analyze(post)
    print(f"Sentiment: {results['sentiment']['label']}")
    print(f"Sentiment Score: {results['sentiment']['score']:.3f}")
    if results['sentiment'].get('vader'):
        vader = results['sentiment']['vader']
        print(f"VADER Breakdown - Positive: {vader['positive']:.2%}, "
              f"Neutral: {vader['neutral']:.2%}, Negative: {vader['negative']:.2%}")

if __name__ == '__main__':
    main()